Phase-resolved prediction of ocean wave field using video prediction

Abstract

Short-term phase-resolved ocean wave field prediction is desired for safe and efficient offshore operation. The dynamics of ocean waves are influenced by ambient currents, nonlinearity, and finite depth, which are difficult to characterize analytically. In this paper, we propose the application of video prediction methods by training the model with in-situ wave characteristics. The problem is set as predicting 5 s future waves in the square area within the predictable zone, using the surface elevation time-series data observed in the $\sim$200 m $\times$ $\sim$200 m range as input. The proposed model was evaluated using publicly available observational ocean wave field data and synthetic wave data compared to the 2D-FFT method based on linear wave theory. As a result, the video prediction showed higher accuracy than 2D-FFT for ocean wave field data. The key to successful wave prediction with observational data could be that the complex wave propagation property in the ocean was learned through in-situ training. Any explicit modeling of physics that can affect the wave propagation property is not necessary for wave prediction with video prediction.